Dev Builds » 20230325-0825

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 15. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.

Summary

Host Duration Avg Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo
ncm-dbt-01 06:59:08 584161 4000 1227 789 1984 +38.2 ± 5.09 5 246 1059 686 4 +77.52 ± 10.4
ncm-dbt-02 07:00:09 587517 4000 1258 827 1915 +37.58 ± 5.21 4 273 1015 704 4 +76.06 ± 10.67
ncm-dbt-03 06:58:10 587529 4000 1253 803 1944 +39.25 ± 5.11 4 242 1064 680 10 +78.44 ± 10.37
ncm-dbt-04 06:58:16 571493 4000 1217 848 1935 +32.14 ± 5.03 3 266 1093 635 3 +64.84 ± 10.21
ncm-dbt-05 07:00:28 584555 4000 1238 815 1947 +36.88 ± 5.08 3 256 1060 677 4 +74.43 ± 10.4
20000 6193 4082 9725 +36.81 ± 2.28 19 1283 5291 3382 25 +74.25 ± 4.65

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
378736 ncm-dbt-05 581818 500 140 99 261 +28.55 ± 13.87 0 33 144 72 1 +56.07 ± 27.96 ↓
378735 ncm-dbt-04 570188 500 155 112 233 +29.95 ± 14.24 0 36 135 79 0 +60.36 ± 29.19 ↓
378734 ncm-dbt-02 588174 500 160 95 245 +45.42 ± 14.41 0 30 125 95 0 +92.46 ± 30.47 ↓
378733 ncm-dbt-03 586435 500 156 103 241 +36.97 ± 13.63 1 23 150 74 2 +73.34 ± 26.95 ↓
378732 ncm-dbt-01 582778 500 152 100 248 +36.26 ± 15.29 1 36 125 86 2 +71.89 ± 30.51 ↓
378731 ncm-dbt-05 585632 500 157 109 234 +33.46 ± 14.74 0 37 129 83 1 +66.1 ± 29.99 ↓
378730 ncm-dbt-02 588387 500 152 109 239 +29.95 ± 13.42 0 29 150 70 1 +58.93 ± 27.08 ↓
378729 ncm-dbt-04 571190 500 159 108 233 +35.56 ± 14.61 0 36 127 87 0 +71.89 ± 30.24 ↓
378728 ncm-dbt-03 587664 500 159 99 242 +41.89 ± 14.61 0 31 130 87 2 +82.1 ± 29.8 ↓
378727 ncm-dbt-01 580489 500 157 102 241 +38.37 ± 13.58 0 27 141 82 0 +77.71 ± 28.25 ↓
378726 ncm-dbt-05 589882 500 156 105 239 +35.56 ± 14.35 0 34 131 85 0 +71.89 ± 29.7 ↓
378725 ncm-dbt-02 586562 500 146 96 258 +34.86 ± 14.44 0 35 130 85 0 +70.44 ± 29.84 ↓
378724 ncm-dbt-04 570308 500 152 116 232 +25.06 ± 14.42 0 38 140 70 2 +47.55 ± 28.56 ↓
378723 ncm-dbt-03 586985 500 145 104 251 +28.55 ± 13.87 0 34 141 75 0 +57.5 ± 28.38 ↓
378722 ncm-dbt-01 583028 500 158 110 232 +33.46 ± 14.35 0 35 132 83 0 +67.55 ± 29.58 ↓
378721 ncm-dbt-02 589839 500 153 105 242 +33.46 ± 15.73 1 42 116 90 1 +67.55 ± 31.69 ↓
378720 ncm-dbt-04 573487 500 149 98 253 +35.56 ± 13.95 0 31 137 82 0 +71.89 ± 28.86 ↓
378719 ncm-dbt-03 587877 500 153 98 249 +38.37 ± 14.4 0 31 135 82 2 +74.79 ± 29.13 ↓
378718 ncm-dbt-05 585211 500 159 105 236 +37.67 ± 14.35 0 33 130 87 0 +76.25 ± 29.82 ↓
378717 ncm-dbt-01 584327 500 159 88 253 +49.67 ± 14.24 1 24 128 97 0 +102.97 ± 29.98 ↓
378716 ncm-dbt-02 588771 500 166 101 233 +45.42 ± 15.19 0 34 119 95 2 +89.48 ± 31.31 ↓
378715 ncm-dbt-04 571230 500 145 100 255 +31.35 ± 13.66 0 31 143 76 0 +63.23 ± 28.06 ↓
378714 ncm-dbt-03 589155 500 155 95 250 +41.89 ± 14.34 0 29 134 85 2 +82.1 ± 29.23 ↓
378713 ncm-dbt-01 587664 500 151 106 243 +31.35 ± 14.07 0 33 140 76 1 +61.79 ± 28.49 ↓
378712 ncm-dbt-05 583572 500 157 99 244 +40.48 ± 14.26 0 31 130 89 0 +82.1 ± 29.8 ↓
378711 ncm-dbt-04 572558 500 150 107 243 +29.95 ± 14.11 0 34 140 75 1 +58.93 ± 28.51 ↓
378710 ncm-dbt-03 588089 500 180 102 218 +54.65 ± 14.49 1 23 124 101 1 +112.14 ± 30.53 ↓
378709 ncm-dbt-02 584537 500 153 100 247 +36.97 ± 15.08 1 36 122 91 0 +76.25 ± 30.91 ↓
378708 ncm-dbt-01 586562 500 151 84 265 +46.84 ± 14.75 1 28 125 95 1 +95.44 ± 30.46 ↓
378707 ncm-dbt-05 582611 500 149 93 258 +39.08 ± 14.44 1 29 134 85 1 +79.17 ± 29.25 ↓
378706 ncm-dbt-04 570108 500 153 106 241 +32.76 ± 14.17 2 28 141 79 0 +68.99 ± 28.31 ↓
378705 ncm-dbt-03 584958 500 150 97 253 +36.97 ± 14.44 0 34 129 87 0 +74.79 ± 29.96 ↓
378704 ncm-dbt-02 589625 500 160 109 231 +35.56 ± 14.61 0 36 127 87 0 +71.89 ± 30.24 ↓
378703 ncm-dbt-01 584285 500 156 110 234 +32.06 ± 14.9 2 34 130 84 0 +67.55 ± 29.85 ↓
378702 ncm-dbt-05 586816 500 159 98 243 +42.6 ± 13.98 1 24 139 85 1 +86.52 ± 28.47 ↓
378701 ncm-dbt-04 572880 500 154 101 245 +36.97 ± 14.57 1 32 130 87 0 +76.25 ± 29.82 ↓
378700 ncm-dbt-03 589069 500 155 105 240 +34.86 ± 15.57 2 37 121 89 1 +71.89 ± 31.04 ↓
378699 ncm-dbt-05 580904 500 161 107 232 +37.67 ± 15.0 1 35 123 91 0 +77.71 ± 30.77 ↓
378698 ncm-dbt-01 584159 500 143 89 268 +37.67 ± 13.81 0 29 138 83 0 +76.25 ± 28.69 ↓
378697 ncm-dbt-02 584243 500 168 112 220 +39.08 ± 14.96 2 31 126 91 0 +82.1 ± 30.36 ↓

Commit

Commit ID 587bc647d7d14b53d8625c4446006e23a4acd82a
Author MinetaS
Date 2023-03-25 08:25:49 UTC
Remove non_pawn_material in NNUE::evaluate After "Use NNUE complexity in search, retune related parameters" commit, the effect of non-pawn material adjustment has been nearly diminished. This patch removes pos.non_pawn_material as a simplification, which passed non-regression tests with both STC and LTC. Passed non-regression STC: LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 75152 W: 20030 L: 19856 D: 35266 Ptnml(0-2): 215, 8281, 20459, 8357, 264 https://tests.stockfishchess.org/tests/view/641ab471db43ab2ba6f7bc58 Passed non-regression LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 193864 W: 51870 L: 51829 D: 90165 Ptnml(0-2): 86, 18968, 58794, 18987, 97 https://tests.stockfishchess.org/tests/view/641b4fe6db43ab2ba6f7db96 closes https://github.com/official-stockfish/Stockfish/pull/4461 Bench: 5020718
Copyright 2011–2024 Next Chess Move LLC
Feedback & Support Terms of Service Privacy Policy